Triple
T3397400
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Yorktown (CV-5) |
E71561
|
entity |
| Predicate | repairedDuration |
P40756
|
FINISHED |
| Object | about 72 hours before Midway |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: about 72 hours before Midway | Statement: [USS Yorktown (CV-5), repairedDuration, about 72 hours before Midway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: repairedDuration Context triple: [USS Yorktown (CV-5), repairedDuration, about 72 hours before Midway]
-
A.
repairedIn
Indicates that an item or object underwent repair within a specified location or during a particular time period.
-
B.
repairDate
Indicates the date on which a repair action was performed or is scheduled to be performed on an entity.
-
C.
actualDuration
chosen
Indicates the real amount of time that an event, process, or activity actually took to complete, as opposed to its planned or estimated duration.
-
D.
repairedInstrument
Indicates that one entity has fixed or restored the proper functioning of a damaged or faulty instrument belonging to or used by another entity.
-
E.
intendedDuration
Indicates the planned or expected length of time for which an action, event, or state is meant to occur or remain in effect.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ad85a9c4a88190a854019341cb3b60 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb8c4099081908a236376b4f86900 |
completed | March 8, 2026, 5:58 p.m. |
| PD | Predicate disambiguation | batch_69adadf705608190975423779430cc58 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:14 p.m.